Add new SentenceTransformer model

README.md

@@ -87,19 +87,19 @@ model-index:
       value: 0.5589816867630893
       name: Cosine Recall@1
     - type: cosine_ndcg@10
-      value: 0.7619419081029518
+      value: 0.7619433934524245
       name: Cosine Ndcg@10
     - type: cosine_mrr@1
       value: 0.5763286334056399
       name: Cosine Mrr@1
     - type: cosine_map@100
-      value: 0.7107794631883741
+      value: 0.7107811578738404
       name: Cosine Map@100
     - type: cosine_auc_precision_cache_hit_ratio
       value: 0.3488530268041688
       name: Cosine Auc Precision Cache Hit Ratio
     - type: cosine_auc_similarity_distribution
-      value: 0.1634818016054941
+      value: 0.16348145891100385
       name: Cosine Auc Similarity Distribution
 ---
 
@@ -112,7 +112,7 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [s
 ### Model Description
 - **Model Type:** Sentence Transformer
 - **Base model:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision c9745ed1d9f207416be6d2e6f8de32d1f16199bf -->
-- **Maximum Sequence Length:** 100 tokens
+- **Maximum Sequence Length:** 256 tokens
 - **Output Dimensionality:** 384 dimensions
 - **Similarity Function:** Cosine Similarity
 - **Training Dataset:**
@@ -130,7 +130,7 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [s
 
 ```
 SentenceTransformer(
-  (0): Transformer({'max_seq_length': 100, 'do_lower_case': False, 'architecture': 'BertModel'})
+  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False, 'architecture': 'BertModel'})
   (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
   (2): Normalize()
 )
@@ -165,9 +165,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 1.0000, 0.3432],
-#         [1.0000, 1.0000, 0.3432],
-#         [0.3432, 0.3432, 1.0001]])
+# tensor([[1.0000, 1.0000, 0.3433],
+#         [1.0000, 1.0000, 0.3433],
+#         [0.3433, 0.3433, 1.0000]])
 ```
 
 <!--
@@ -239,7 +239,7 @@ You can finetune this model on your own dataset.
   |         | anchor                                                                             | positive                                                                           | negative                                                                          |
   |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
   | type    | string                                                                             | string                                                                             | string                                                                            |
-  | details | <ul><li>min: 4 tokens</li><li>mean: 27.15 tokens</li><li>max: 100 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 26.59 tokens</li><li>max: 100 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 19.39 tokens</li><li>max: 64 tokens</li></ul> |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 27.17 tokens</li><li>max: 120 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 26.61 tokens</li><li>max: 120 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 19.39 tokens</li><li>max: 64 tokens</li></ul> |
 * Samples:
   | anchor                                                                                        | positive                                                                                      | negative                                                                                       |
   |:----------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------|
@@ -266,7 +266,7 @@ You can finetune this model on your own dataset.
   |         | anchor                                                                             | positive                                                                           | negative                                                                          |
   |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
   | type    | string                                                                             | string                                                                             | string                                                                            |
-  | details | <ul><li>min: 4 tokens</li><li>mean: 27.15 tokens</li><li>max: 100 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 26.59 tokens</li><li>max: 100 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 19.39 tokens</li><li>max: 64 tokens</li></ul> |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 27.17 tokens</li><li>max: 120 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 26.61 tokens</li><li>max: 120 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 19.39 tokens</li><li>max: 64 tokens</li></ul> |
 * Samples:
   | anchor                                                                                        | positive                                                                                      | negative                                                                                       |
   |:----------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------|
@@ -296,7 +296,7 @@ You can finetune this model on your own dataset.
 - `warmup_ratio`: 0.05
 - `bf16`: True
 - `dataloader_num_workers`: 6
-- `dataloader_prefetch_factor`: 2
+- `dataloader_prefetch_factor`: 1
 - `load_best_model_at_end`: True
 - `optim`: stable_adamw
 - `ddp_find_unused_parameters`: False
@@ -359,7 +359,7 @@ You can finetune this model on your own dataset.
 - `debug`: []
 - `dataloader_drop_last`: False
 - `dataloader_num_workers`: 6
-- `dataloader_prefetch_factor`: 2
+- `dataloader_prefetch_factor`: 1
 - `past_index`: -1
 - `disable_tqdm`: False
 - `remove_unused_columns`: True

config.json

@@ -4,7 +4,7 @@
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "dtype": "bfloat16",
+  "dtype": "float32",
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec3cf21b9dac967ed24a078c8554f9c345e2b737507a2bd9751787934fc0930f
-size 45437864
+oid sha256:fcea1769de0d43888c0612653d804fb22f13517e64b92633b2c7436d1ee565ae
+size 90864192

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-    "max_seq_length": 100,
+    "max_seq_length": 256,
     "do_lower_case": false
 }